Flexan/kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF

Same weights, converted vs kshitijthakkar/qwen3.5-moe-0.87B-d0.8B. Same weights stored in another dtype (BF16 → F16/F32), plus 90 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/61, MLP 0/120, Attention 0/24

On the Hub · Downloads on Model Pulse